{"id":"W4221135459","doi":"10.1002/9781119078166.ch11","title":"Reinforcement Learning‐Based Filter","year":2022,"lang":"en","type":"other","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reinforcement learning; Inference; Computer science; Artificial intelligence; Reinforcement; Equivalence (formal languages); Maximization; Machine learning; Unsupervised learning; Mathematical optimization; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008147555,0.0007162921,0.0010587,0.0003285194,0.0003695553,0.00123828,0.0008702112,0.0009945385,0.009574382],"category_scores_gemma":[0.002727356,0.0002552645,0.000500483,0.000399012,0.0006600791,0.0008485047,0.0007648282,0.001418617,0.001781735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008825185,"about_ca_system_score_gemma":0.001037289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004700043,"about_ca_topic_score_gemma":0.003903997,"domain_scores_codex":[0.9996057,0.00008925574,0.00002186843,0.000101921,0.0001285366,0.0000526635],"domain_scores_gemma":[0.999411,0.000337185,0.00004218012,0.00004665571,0.000136398,0.00002663183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009981556,0.00007190693,0.0005005741,0.0001814819,0.00007532836,0.00007578693,0.00005848044,0.6857392,0.003505958,0.1199787,0.006937745,0.182775],"study_design_scores_gemma":[0.00001353468,0.00002604438,0.00008963292,0.00001486442,0.00000954451,0.00001813636,0.00000371567,0.9787011,0.0006461355,0.01693984,0.003529973,0.000007402238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.002397302,0.00054648,0.9864792,0.0002172081,0.0001209907,0.0000318489,0.00005976831,0.0003585257,0.009788647],"genre_scores_gemma":[0.7052531,0.002757891,0.2415704,0.0006154016,0.0003794731,0.0004080268,0.0005054044,0.0002555566,0.04825471],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.009574382,"threshold_uncertainty_score":0.03202951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007194081828015181,"score_gpt":0.1805173071234988,"score_spread":0.1733232252954837,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}